novita-docs

SKILL.md

Novita AI Platform Reference

Complete documentation for the Novita AI platform - an AI & Agent Cloud for developers.

When to Use This Skill

Load this skill when the user asks about:

  • Novita AI products: Model APIs, GPU instances, serverless GPUs, agent sandbox
  • Model information: "What models does Novita support?", model pricing, capabilities
  • API guidance: How to use APIs, authentication, endpoints, parameters
  • Pricing and billing: Cost estimates, billing queries, payment methods
  • Integrations: LangChain, LlamaIndex, Cursor, and 30+ other tools
  • Design system: Colors, typography, buttons, navigation, icons, logo
  • Getting started: Quickstart guides, FAQs, setup instructions
  • Troubleshooting: Error codes, common issues, support

Quick Reference

Resource URL
Website https://novita.ai
Model Catalog https://novita.ai/models (200+ models)
Documentation https://novita.ai/docs
Pricing https://novita.ai/pricing
Console https://novita.ai/console
API Base URL https://api.novita.ai/openai
Support support@novita.ai
Discord https://discord.gg/YyPRAzwp7P

๐Ÿ” Quick: Query Available Models

Most common question: "What models does Novita support?"

Query Methods

1. Web Catalog (human-friendly):

2. API Endpoint (automation):

curl https://api.novita.ai/openai/v1/models \
  -H "Authorization: Bearer <YOUR_API_KEY>"

Returns: Model ID, pricing per million tokens, context size, description

Model Categories

  • LLMs: 100+ models (Llama, Qwen, DeepSeek, Mistral, etc.)
  • Image Generation: Flux, Stable Diffusion, SDXL
  • Video: Wan 2.6, CogVideoX
  • Audio: TTS, voice cloning
  • Embeddings: Text embedding models

Quick Links

Task Reference
List all models via API list-models.md
Get specific model info retrieve-model.md
Recommended LLMs llm/recommended.md
Image model APIs api-reference/image-apis/
Model API guides model-apis/

Pro Tip: Always call /v1/models API first for the latest model list and current pricing.


How to Use This Documentation

1. Start Here

  • New users: See getting-started/ - company overview, quickstart, FAQ
  • Model queries: Check the "Quick: Query Available Models" section above
  • API help: Jump to specific API reference sections below

2. Find Documentation by Category

Product Guides (usage and features):

API Reference (endpoints and parameters):

Support:

  • billing/ - Billing and payments (4 files)
  • team/ - Team management (1 file)

Design System:

3. File Naming Convention

Files are organized by category:

references/
โ”œโ”€โ”€ getting-started/          # Product overviews and quickstart
โ”œโ”€โ”€ llm/                      # LLM feature guides
โ”œโ”€โ”€ model-apis/               # Model API guides
โ”œโ”€โ”€ gpu-instance/             # GPU instance guides
โ”œโ”€โ”€ serverless-gpus/          # Serverless GPU guides
โ”œโ”€โ”€ sandbox/                  # Agent Sandbox docs (with subdirs)
โ”œโ”€โ”€ integrations/             # Third-party tool integrations
โ”œโ”€โ”€ api-reference/            # API endpoint documentation
โ”‚   โ”œโ”€โ”€ basic/               # Auth, billing APIs
โ”‚   โ”œโ”€โ”€ llm/                 # LLM API endpoints
โ”‚   โ”œโ”€โ”€ image-apis/          # Image/video API endpoints
โ”‚   โ””โ”€โ”€ gpu-instance/        # GPU instance APIs
โ”œโ”€โ”€ billing/                  # Billing and payment
โ”œโ”€โ”€ team/                     # Team management
โ””โ”€โ”€ design-system/            # UI/UX design specs

๐Ÿ“š Documentation Index

Core Product Documentation

Getting Started (8 files)

LLM Guides (17 files) Core: api ยท batch-api ยท function-calling ยท vision ยท reasoning ยท structured-outputs ยท prompt-cache ยท rate-limits ยท monitoring ยท observability-metrics ยท dedicated-endpoint ยท playgrounds ยท recommended

Model APIs (11 files) overview ยท sdks ยท dedicated-endpoints ยท training-guidance ยท custom-model ยท sampler ยท vae ยท clip-skip ยท rate-limits ยท v2-to-v3-migration ยท configure-custom-s3-bucket

GPU Instance (14 files) overview ยท overview-guide ยท choose-a-gpu ยท pricing ยท quickstart-* (5 files) ยท jupyterlab ยท save-image ยท upgrade-instance ยท edit-instance ยท image-prewarm

Serverless GPUs (6 files) overview ยท pricing ยท quickstart-* (4 files)

Agent Sandbox (43 files organized in subdirectories) Core: overview ยท pricing ยท sdk-and-cli

Quickstart: your-first-sandbox ยท introduction ยท installation ยท quick-start ยท frameworks ยท advanced

CLI: overview ยท auth ยท spawn ยท list ยท shutdown

Commands: overview ยท background ยท streaming

Filesystem: overview ยท read-write ยท upload ยท download ยท watch

Lifecycle: overview ยท clone ยท list ยท idle-timeout

Template: overview ยท customize-cpu-ram ยท start-cmd ยท ready-cmd ยท version-management

More: console ยท connect ยท internet-access ยท environment-variables ยท metadata ยท metrics ยท mount-cloudstorage

Integrations (30 tools) langchain ยท llamaindex ยท huggingface ยท cursor ยท dify ยท browseruse ยท skyvern ยท gradio ยท anythingllm ยท axolotl ยท chatbox ยท claude-code ยท codecompanion ยท continue ยท deepsearcher ยท docsgpt ยท helicone ยท kohya-ss-gui ยท langflow ยท langfuse ยท litellm ยท lobechat ยท lollms-webui ยท openai-agents-sdk ยท owl ยท pageassist ยท portkey ยท verba

API Reference

Basic APIs (6 files) authentication ยท error-code ยท get-user-balance ยท query-*-billing (3 files)

LLM APIs (16 files) list-models ยท retrieve-model ยท create-chat-completion ยท create-completion ยท create-embeddings ยท create-rerank ยท create-batch ยท cancel-batch ยท list-batches ยท retrieve-batch ยท list-files ยท upload-batch-input-file ยท query-file ยท retrieve-file-content ยท delete-file

Image/Video APIs (54 files) introduction

Core APIs: txt2img ยท img2img ยท inpainting ยท upscale ยท image-upscaler ยท remove-background ยท image-to-prompt ยท eraser ยท remove-text ยท replace-background ยท merge-face ยท reimagine ยท video-merge-face ยท task-result

Flux Models: flux-1-schnell ยท flux-1-kontext-dev ยท flux-1-kontext-max ยท flux-1-kontext-pro ยท flux-2-dev ยท flux-2-flex ยท flux-2-pro

Other Models: seedream-* (3) ยท glm-image ยท hunyuan-image-3 ยท qwen-* (2) ยท z-image-turbo ยท z-image-turbo-lora

Training: create-style-training ยท create-subject-training ยท list-training-task ยท get-training-images-url

Other: glm-tts-voice-clone ยท webhook

GPU Instance APIs (2 files) create-instance ยท list-clusters

Support & Design System

Billing (4 files) budgets ยท auto-top-up ยท payment-methods ยท low-balance-alert

Team (1 file) team-management

Design System (7 files) overview ยท typography ยท colors ยท buttons ยท navigation ยท icons ยท logo


Common Tasks

Start with Model APIs

  1. Get API key from https://novita.ai/console
  2. Set base URL to https://api.novita.ai/openai
  3. Call /v1/models to list available models
  4. Use OpenAI-compatible APIs for chat completions
  5. See llm/api.md for details

Launch GPU Instance

  1. Go to https://novita.ai/gpus-console/explore
  2. Choose GPU or template
  3. Configure and launch
  4. Connect via SSH or web terminal
  5. See gpu-instance/ for details

Create Serverless Endpoint

  1. Prepare container image
  2. Go to https://novita.ai/gpus-console/serverless
  3. Create endpoint with scale policy
  4. Test and deploy
  5. See serverless-gpus/ for details

Start Agent Sandbox

  1. Install SDK or CLI
  2. Create sandbox with desired resources
  3. Run commands or upload code
  4. Pause/resume as needed
  5. See sandbox/ for details

Integrate with Framework

  1. Get Novita API key
  2. Set base URL to https://api.novita.ai/openai
  3. Update model names as needed
  4. See integrations/ for specific guides

Support & Resources

Weekly Installs
6
First Seen
Feb 9, 2026
Installed on
opencode6
gemini-cli6
github-copilot6
codex6
kimi-cli6
amp6